Neural Turing Machines (contributions)
E260059
Neural Turing Machines (contributions) refers to Oriol Vinyals’s work on augmenting neural networks with differentiable external memory to enable algorithmic reasoning and sequence learning beyond traditional architectures.
All labels observed (3)
| Label | Occurrences |
|---|---|
| Neural Turing Machines | 2 |
| Neural Turing Machines (contributions) canonical | 1 |
| Neural Turing Machines paper | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T2373763 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neural Turing Machines (contributions) Context triple: [Oriol Vinyals, notableWork, Neural Turing Machines (contributions)]
-
A.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
B.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
C.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
D.
Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
-
E.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Neural Turing Machines (contributions) Target entity description: Neural Turing Machines (contributions) refers to Oriol Vinyals’s work on augmenting neural networks with differentiable external memory to enable algorithmic reasoning and sequence learning beyond traditional architectures.
-
A.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
B.
Intriguing properties of neural networks
"Intriguing properties of neural networks" is a highly influential research paper that revealed surprising vulnerabilities and behaviors of deep neural networks, particularly their susceptibility to adversarial examples.
-
C.
Boltzmann machines
Boltzmann machines are stochastic recurrent neural networks used for learning complex probability distributions, foundational in unsupervised learning and energy-based models.
-
D.
Inception architecture
The Inception architecture is a deep convolutional neural network design that introduced parallel multi-scale processing modules to achieve state-of-the-art image recognition performance with improved computational efficiency.
-
E.
Hopfield networks
Hopfield networks are recurrent artificial neural networks that serve as content-addressable memory systems, storing patterns as stable states and retrieving them through dynamics that minimize an energy function.
- F. None of above. chosen
Statements (45)
| Predicate | Object |
|---|---|
| instanceOf |
differentiable computer model
ⓘ
memory-augmented neural network ⓘ neural network architecture ⓘ |
| addresses | limitations of standard RNNs on algorithmic tasks ⓘ |
| contribution |
bridged connectionist models and symbolic computation
ⓘ
introduced differentiable external memory for neural networks ⓘ provided a framework for program-like behavior in neural networks ⓘ showed neural networks can learn simple algorithms from examples ⓘ |
| controllerType | recurrent neural network controller ⓘ |
| demonstratedOn |
associative recall task
ⓘ
copy task ⓘ priority sort task ⓘ repeat-copy task ⓘ |
| enables |
algorithmic reasoning
ⓘ
learning simple algorithms from data ⓘ sequence learning ⓘ |
| extends | recurrent neural networks ⓘ |
| field |
deep learning
ⓘ
machine learning ⓘ |
| hasAuthor |
Alex Graves
ⓘ
Greg Wayne ⓘ Ivo Danihelka ⓘ |
| hasComponent |
controller network
ⓘ
read head ⓘ write head ⓘ |
| hasContributor |
DeepMind
ⓘ
Oriol Vinyals ⓘ |
| hasExternalMemory | differentiable memory matrix ⓘ |
| hasImpactOn |
algorithmic task benchmarks in deep learning
ⓘ
sequence-to-sequence learning research ⓘ |
| hasTitle | Neural Turing Machines ⓘ |
| influenced |
research on differentiable programming
ⓘ
research on neural program induction ⓘ |
| inspired |
Differentiable Neural Computers
ⓘ
surface form:
Differentiable Neural Computer
subsequent memory-augmented neural networks ⓘ |
| organization | developed at DeepMind ⓘ |
| publicationYear | 2014 ⓘ |
| publishedAs | arXiv preprint arXiv:1410.5401 ⓘ |
| relatedTo |
Turing machine
ⓘ
neural networks with external memory ⓘ |
| supports | end-to-end differentiable memory access ⓘ |
| trainedWith |
backpropagation through time
ⓘ
gradient descent ⓘ |
| uses |
content-based addressing
ⓘ
location-based addressing ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Neural Turing Machines (contributions) Description of subject: Neural Turing Machines (contributions) refers to Oriol Vinyals’s work on augmenting neural networks with differentiable external memory to enable algorithmic reasoning and sequence learning beyond traditional architectures.
Referenced by (4)
Full triples — surface form annotated when it differs from this entity's canonical label.
this entity surface form:
Neural Turing Machines
this entity surface form:
Neural Turing Machines
this entity surface form:
Neural Turing Machines paper